An adaptive projected subgradient approach to learning in diffusion networks
IEEE Transactions on Signal Processing
An output signal based combination of two NLMS adaptive algorithms
DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
Improved adaptive filtering schemes via adaptive combination
Asilomar'09 Proceedings of the 43rd Asilomar conference on Signals, systems and computers
Asilomar'09 Proceedings of the 43rd Asilomar conference on Signals, systems and computers
Steady-state MSE performance analysis of mixture approaches to adaptive filtering
IEEE Transactions on Signal Processing
Transient and steady-state analysis of the affine combination of two adaptive filters
IEEE Transactions on Signal Processing
Unbiased model combinations for adaptive filtering
IEEE Transactions on Signal Processing
Adaptively biasing the weights of adaptive filters
IEEE Transactions on Signal Processing
An adaptive sensor array using an affine combination of two filters
SITE'12 Proceedings of the 11th international conference on Telecommunications and Informatics, Proceedings of the 11th international conference on Signal Processing
Adaptive mixture methods based on Bregman divergences
Digital Signal Processing
| Hi-index | 35.70 |
This paper studies the statistical behavior of an affine combination of the outputs of two least mean-square (LMS) adaptive filters that simultaneously adapt using the same white Gaussian inputs. The purpose of the combination is to obtain an LMS adaptive filter with fast convergence and small steady-state mean-square deviation (MSD). The linear combination studied is a generalization of the convex combination, in which the combination factor lambda(n) is restricted to the interval (0,1). The viewpoint is taken that each of the two filters produces dependent estimates of the unknown channel. Thus, there exists a sequence of optimal affine combining coefficients which minimizes the mean-square error (MSE). First, the optimal unrealizable affine combiner is studied and provides the best possible performance for this class. Then two new schemes are proposed for practical applications. The mean-square performances are analyzed and validated by Monte Carlo simulations. With proper design, the two practical schemes yield an overall MSD that is usually less than the MSDs of either filter.